In [1]:

import matplotlib.pyplot as plt
import matplotlib
import numpy as np
import pandas as pd

%matplotlib inline

In [2]:

print(f"Pandas version: {pd.__version__}, matplotlib version: {matplotlib.__version__}")

Pandas version: 1.3.2, matplotlib version: 3.4.3

example 1¶

In [3]:

df = pd.DataFrame({
    'name':['john','mary','peter','jeff','bill','lisa','jose'],
    'age':[23,78,22,19,45,33,20],
    'gender':['M','F','M','M','M','F','M'],
    'state':['california','dc','california','dc','california','texas','texas'],
    'num_children':[2,0,0,3,2,1,4],
    'num_pets':[5,1,0,5,2,2,3]
})
df[['name','age','gender','state','num_children','num_pets']]

Out[3]:

	name	age	gender	state	num_children	num_pets
0	john	23	M	california	2	5
1	mary	78	F	dc	0	1
2	peter	22	M	california	0	0
3	jeff	19	M	dc	3	5
4	bill	45	M	california	2	2
5	lisa	33	F	texas	1	2
6	jose	20	M	texas	4	3

In [4]:

df.plot(kind='scatter',x='num_children',y='num_pets',color='red')

Out[4]:

<AxesSubplot:xlabel='num_children', ylabel='num_pets'>

No description has been provided for this image

In [5]:

df.plot(kind='bar',x='name',y='age')

Out[5]:

<AxesSubplot:xlabel='name'>

In [6]:

plt.clf()
# gca stands for 'get current axis'
ax = plt.gca()

df.plot(kind='line',x='name',y='num_children',ax=ax)
df.plot(kind='line',x='name',y='num_pets', color='red', ax=ax)

plt.show()

In [7]:

df.groupby('state').size().plot(kind='bar')

Out[7]:

<AxesSubplot:xlabel='state'>

In [8]:

df.groupby(['state','gender']).size().unstack().plot(kind='bar',stacked=True)
plt.show()

In [9]:

plt.clf()
df.groupby(['gender','state']).size().unstack().plot(kind='bar',stacked=True)
plt.legend(loc='lower right')
plt.gcf().set_size_inches(7,4)
plt.show()

<Figure size 432x288 with 0 Axes>

plot histogram for dataframe column¶

In [10]:

df[['age']].plot(kind='hist',bins=[0,20,40,60,80,100],rwidth=0.9)

Out[10]:

<AxesSubplot:ylabel='Frequency'>

stacked bar plot¶

In [11]:

import matplotlib.pyplot as plt

# create dummy variable them group by that
# set the legend to false because we'll fix it later
df.assign(
 dummy = 1   
).groupby(['dummy','state']).size().to_frame().unstack().plot(kind='bar',stacked=True,legend=False)

plt.title('Number of records by State')

# other it'll show up as 'dummy' 
plt.xlabel('state')

# disable ticks in the x axis
plt.xticks([])

# fix the legend
current_handles, _ = plt.gca().get_legend_handles_labels()
reversed_handles = reversed(current_handles)

labels = reversed(df['state'].unique())

plt.legend(reversed_handles,labels,loc='lower right')

plt.gcf().set_size_inches(7,4)
plt.show()

Stacked bar plot percentages¶

In [12]:

import matplotlib.pyplot as plt
import matplotlib.ticker as mtick

# create dummy variable them group by that
# set the legend to false because we'll fix it later
df.assign(
 dummy = 1   
).groupby(['dummy','state']).size().groupby(level=0).apply(
    lambda x: 100 * x / x.sum()
).to_frame().unstack().plot(kind='bar',stacked=True,legend=False)


plt.title('Amount of records by State, normalized')


# other it'll show up as 'dummy' 
plt.xlabel('state')

# disable ticks in the x axis
plt.xticks([])

# fix the legend
current_handles, _ = plt.gca().get_legend_handles_labels()
reversed_handles = reversed(current_handles)

labels = reversed(df['state'].unique())

plt.legend(reversed_handles,labels,loc='lower right')

plt.gcf().set_size_inches(7,4)
plt.gca().yaxis.set_major_formatter(mtick.PercentFormatter())
plt.show()

percent, two-level group by¶

In [13]:

import matplotlib.ticker as mtick

df.groupby(['gender','state']).size().groupby(level=0).apply(
    lambda x: 100 * x / x.sum()
).unstack().plot(kind='bar',stacked=True,legend='reverse')

plt.gca().yaxis.set_major_formatter(mtick.PercentFormatter())
plt.title('Amount of records by Gender and State, normalized')
# plt.legend(loc='lower right')
plt.gcf().set_size_inches(7,4)
plt.show()

date histograms¶

In [20]:

df = pd.DataFrame({
    'name':['john','lisa','peter','carl','linda','betty'],
    'date_of_birth':[
        '01/21/1988','03/10/1977','07/25/1999','01/22/1977','09/30/1968','09/15/1970'
    ]
})

df

Out[20]:

	name	date_of_birth
0	john	01/21/1988
1	lisa	03/10/1977
2	peter	07/25/1999
3	carl	01/22/1977
4	linda	09/30/1968
5	betty	09/15/1970

In [21]:

df['date_of_birth'] = pd.to_datetime(df['date_of_birth'], infer_datetime_format=True)

In [22]:

df.dtypes

Out[22]:

name                     object
date_of_birth    datetime64[ns]
dtype: object

In [26]:

plt.clf()
df['date_of_birth'].map(lambda d: d.month).plot(kind='hist')
# plt.xlabel('Month number')
plt.show()

In [31]:

df.set_index(df['date_of_birth']).asfreq('M')

Out[31]:

	name	date_of_birth
date_of_birth
1968-09-30	linda	1968-09-30
1968-10-31	NaN	NaT
1968-11-30	NaN	NaT
1968-12-31	NaN	NaT
1969-01-31	NaN	NaT
...	...	...
1999-02-28	NaN	NaT
1999-03-31	NaN	NaT
1999-04-30	NaN	NaT
1999-05-31	NaN	NaT
1999-06-30	NaN	NaT

370 rows × 2 columns

In [ ]: